Identification of Physiologic Biomarkers in Patients with ObstructiveSleep Apnea (OSA): A Step Towards a Precision Care Approach
Obstructive sleep apnea (OSA) is a common disease characterized by recurrent collapse of the airway during sleep leading to sleep fragmentation and daytime sleepiness. OSA is usually diagnosed based on an overnight sleep study (polysomnogram) which collects detailed physiologic information over the night. OSA patients are also at increased risk of cardiovascular disease such as heart attacks and strokes. However, it is difficult to predict which patients are at particularly high risk; knowing which patients are at greatest risk would be helpful in guiding therapy as they would be candidates for more aggressive OSA therapy and cardiovascular risk reduction. Currently, one neglected opportunity is more in depth analysis of the polysomnogram as currently, very little of the data is used in clinical decision making. The purpose of this project is to use a large dataset of patients studied with a sleep study (1500 patients) who have detailed demographic and symptom data. These patients will be linked to population databases to ascertain validated cardiovascular events in them. Using advanced signal processing and machine learning techniques, information from the polysomnogram (and clinical data) will be used to develop a robust prediction model.